5 files changed, 331 insertions, 61 deletions

diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile
index df79910192d6..8a2c64dc9641 100644
--- a/drivers/net/ipvlan/Makefile
+++ b/drivers/net/ipvlan/Makefile
@@ -3,5 +3,6 @@
 #
 
 obj-$(CONFIG_IPVLAN) += ipvlan.o
+obj-$(CONFIG_IPVTAP) += ipvtap.o
 
 ipvlan-objs := ipvlan_core.o ipvlan_main.o
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index dbfbb33ac66c..800a46c8d26c 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -94,9 +94,11 @@ struct ipvl_port {
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	struct list_head	ipvlans;
 	u16			mode;
+	u16			dev_id_start;
 	struct work_struct	wq;
 	struct sk_buff_head	backlog;
 	int			count;
+	struct ida		ida;
 };
 
 struct ipvl_skb_cb {
@@ -133,4 +135,11 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb,
 			      u16 proto);
 unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb,
 			     const struct nf_hook_state *state);
+void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+		     unsigned int len, bool success, bool mcast);
+int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+		    struct nlattr *tb[], struct nlattr *data[]);
+void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
+void ipvlan_link_setup(struct net_device *dev);
+int ipvlan_link_register(struct rtnl_link_ops *ops);
 #endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 83ce74acf82d..1f3295e274d0 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -16,12 +16,9 @@ void ipvlan_init_secret(void)
 	net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret));
 }
 
-static void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 			    unsigned int len, bool success, bool mcast)
 {
-	if (!ipvlan)
-		return;
-
 	if (likely(success)) {
 		struct ipvl_pcpu_stats *pcptr;
 
@@ -36,6 +33,7 @@ static void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 		this_cpu_inc(ipvlan->pcpu_stats->rx_errs);
 	}
 }
+EXPORT_SYMBOL_GPL(ipvlan_count_rx);
 
 static u8 ipvlan_get_v6_hash(const void *iaddr)
 {
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 8b0f99300cbc..aa8575ccbce3 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -102,8 +102,8 @@ static int ipvlan_port_create(struct net_device *dev)
 		return -EINVAL;
 	}
 
-	if (netif_is_macvlan_port(dev)) {
-		netdev_err(dev, "Master is a macvlan port.\n");
+	if (netdev_is_rx_handler_busy(dev)) {
+		netdev_err(dev, "Device is already in use.\n");
 		return -EBUSY;
 	}
 
@@ -119,6 +119,8 @@ static int ipvlan_port_create(struct net_device *dev)
 
 	skb_queue_head_init(&port->backlog);
 	INIT_WORK(&port->wq, ipvlan_process_multicast);
+	ida_init(&port->ida);
+	port->dev_id_start = 1;
 
 	err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port);
 	if (err)
@@ -150,6 +152,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 			dev_put(skb->dev);
 		kfree_skb(skb);
 	}
+	ida_destroy(&port->ida);
 	kfree(port);
 }
 
@@ -301,8 +304,8 @@ static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
 	dev_mc_sync(ipvlan->phy_dev, dev);
 }
 
-static struct rtnl_link_stats64 *ipvlan_get_stats64(struct net_device *dev,
-						    struct rtnl_link_stats64 *s)
+static void ipvlan_get_stats64(struct net_device *dev,
+			       struct rtnl_link_stats64 *s)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
@@ -339,7 +342,6 @@ static struct rtnl_link_stats64 *ipvlan_get_stats64(struct net_device *dev,
 		s->rx_dropped = rx_errs;
 		s->tx_dropped = tx_drps;
 	}
-	return s;
 }
 
 static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
@@ -494,8 +496,8 @@ err:
 	return ret;
 }
 
-static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[])
+int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+		    struct nlattr *tb[], struct nlattr *data[])
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_port *port;
@@ -533,6 +535,29 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 
+	/* If the port-id base is at the MAX value, then wrap it around and
+	 * begin from 0x1 again. This may be due to a busy system where lots
+	 * of slaves are getting created and deleted.
+	 */
+	if (port->dev_id_start == 0xFFFE)
+		port->dev_id_start = 0x1;
+
+	/* Since L2 address is shared among all IPvlan slaves including
+	 * master, use unique 16 bit dev-ids to diffentiate among them.
+	 * Assign IDs between 0x1 and 0xFFFE (used by the master) to each
+	 * slave link [see addrconf_ifid_eui48()].
+	 */
+	err = ida_simple_get(&port->ida, port->dev_id_start, 0xFFFE,
+			     GFP_KERNEL);
+	if (err < 0)
+		err = ida_simple_get(&port->ida, 0x1, port->dev_id_start,
+				     GFP_KERNEL);
+	if (err < 0)
+		goto destroy_ipvlan_port;
+	dev->dev_id = err;
+	/* Increment id-base to the next slot for the future assignment */
+	port->dev_id_start = err + 1;
+
 	/* TODO Probably put random address here to be presented to the
 	 * world but keep using the physical-dev address for the outgoing
 	 * packets.
@@ -543,7 +568,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 
 	err = register_netdevice(dev);
 	if (err < 0)
-		goto destroy_ipvlan_port;
+		goto remove_ida;
 
 	err = netdev_upper_dev_link(phy_dev, dev);
 	if (err) {
@@ -562,13 +587,16 @@ unlink_netdev:
 	netdev_upper_dev_unlink(phy_dev, dev);
 unregister_netdev:
 	unregister_netdevice(dev);
+remove_ida:
+	ida_simple_remove(&port->ida, dev->dev_id);
 destroy_ipvlan_port:
 	if (create)
 		ipvlan_port_destroy(phy_dev);
 	return err;
 }
+EXPORT_SYMBOL_GPL(ipvlan_link_new);
 
-static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
@@ -579,12 +607,14 @@ static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 		kfree_rcu(addr, rcu);
 	}
 
+	ida_simple_remove(&ipvlan->port->ida, dev->dev_id);
 	list_del_rcu(&ipvlan->pnode);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
 }
+EXPORT_SYMBOL_GPL(ipvlan_link_delete);
 
-static void ipvlan_link_setup(struct net_device *dev)
+void ipvlan_link_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
@@ -595,6 +625,7 @@ static void ipvlan_link_setup(struct net_device *dev)
 	dev->header_ops = &ipvlan_header_ops;
 	dev->ethtool_ops = &ipvlan_ethtool_ops;
 }
+EXPORT_SYMBOL_GPL(ipvlan_link_setup);
 
 static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
 {
@@ -605,22 +636,22 @@ static struct rtnl_link_ops ipvlan_link_ops = {
 	.kind		= "ipvlan",
 	.priv_size	= sizeof(struct ipvl_dev),
 
-	.get_size	= ipvlan_nl_getsize,
-	.policy		= ipvlan_nl_policy,
-	.validate	= ipvlan_nl_validate,
-	.fill_info	= ipvlan_nl_fillinfo,
-	.changelink	= ipvlan_nl_changelink,
-	.maxtype	= IFLA_IPVLAN_MAX,
-
 	.setup		= ipvlan_link_setup,
 	.newlink	= ipvlan_link_new,
 	.dellink	= ipvlan_link_delete,
 };
 
-static int ipvlan_link_register(struct rtnl_link_ops *ops)
+int ipvlan_link_register(struct rtnl_link_ops *ops)
 {
+	ops->get_size	= ipvlan_nl_getsize;
+	ops->policy	= ipvlan_nl_policy;
+	ops->validate	= ipvlan_nl_validate;
+	ops->fill_info	= ipvlan_nl_fillinfo;
+	ops->changelink = ipvlan_nl_changelink;
+	ops->maxtype	= IFLA_IPVLAN_MAX;
 	return rtnl_link_register(ops);
 }
+EXPORT_SYMBOL_GPL(ipvlan_link_register);
 
 static int ipvlan_device_event(struct notifier_block *unused,
 			       unsigned long event, void *ptr)
@@ -674,23 +705,22 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	return NOTIFY_DONE;
 }
 
-static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
 {
 	struct ipvl_addr *addr;
 
-	if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) {
-		netif_err(ipvlan, ifup, ipvlan->dev,
-			  "Failed to add IPv6=%pI6c addr for %s intf\n",
-			  ip6_addr, ipvlan->dev->name);
-		return -EINVAL;
-	}
 	addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC);
 	if (!addr)
 		return -ENOMEM;
 
 	addr->master = ipvlan;
-	memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr));
-	addr->atype = IPVL_IPV6;
+	if (is_v6) {
+		memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr));
+		addr->atype = IPVL_IPV6;
+	} else {
+		memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr));
+		addr->atype = IPVL_IPV4;
+	}
 	list_add_tail(&addr->anode, &ipvlan->addrs);
 
 	/* If the interface is not up, the address will be added to the hash
@@ -702,11 +732,11 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
 	return 0;
 }
 
-static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
 {
 	struct ipvl_addr *addr;
 
-	addr = ipvlan_find_addr(ipvlan, ip6_addr, true);
+	addr = ipvlan_find_addr(ipvlan, iaddr, is_v6);
 	if (!addr)
 		return;
 
@@ -717,6 +747,23 @@ static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
 	return;
 }
 
+static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) {
+		netif_err(ipvlan, ifup, ipvlan->dev,
+			  "Failed to add IPv6=%pI6c addr for %s intf\n",
+			  ip6_addr, ipvlan->dev->name);
+		return -EINVAL;
+	}
+
+	return ipvlan_add_addr(ipvlan, ip6_addr, true);
+}
+
+static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+	return ipvlan_del_addr(ipvlan, ip6_addr, true);
+}
+
 static int ipvlan_addr6_event(struct notifier_block *unused,
 			      unsigned long event, void *ptr)
 {
@@ -750,45 +797,19 @@ static int ipvlan_addr6_event(struct notifier_block *unused,
 
 static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
 {
-	struct ipvl_addr *addr;
-
 	if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) {
 		netif_err(ipvlan, ifup, ipvlan->dev,
 			  "Failed to add IPv4=%pI4 on %s intf.\n",
 			  ip4_addr, ipvlan->dev->name);
 		return -EINVAL;
 	}
-	addr = kzalloc(sizeof(struct ipvl_addr), GFP_KERNEL);
-	if (!addr)
-		return -ENOMEM;
-
-	addr->master = ipvlan;
-	memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr));
-	addr->atype = IPVL_IPV4;
-	list_add_tail(&addr->anode, &ipvlan->addrs);
 
-	/* If the interface is not up, the address will be added to the hash
-	 * list by ipvlan_open.
-	 */
-	if (netif_running(ipvlan->dev))
-		ipvlan_ht_addr_add(ipvlan, addr);
-
-	return 0;
+	return ipvlan_add_addr(ipvlan, ip4_addr, false);
 }
 
 static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
 {
-	struct ipvl_addr *addr;
-
-	addr = ipvlan_find_addr(ipvlan, ip4_addr, false);
-	if (!addr)
-		return;
-
-	ipvlan_ht_addr_del(addr);
-	list_del(&addr->anode);
-	kfree_rcu(addr, rcu);
-
-	return;
+	return ipvlan_del_addr(ipvlan, ip4_addr, false);
 }
 
 static int ipvlan_addr4_event(struct notifier_block *unused,
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
new file mode 100644
index 000000000000..2b713b63b62c
--- /dev/null
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -0,0 +1,241 @@
+#include <linux/etherdevice.h>
+#include "ipvlan.h"
+#include <linux/if_vlan.h>
+#include <linux/if_tap.h>
+#include <linux/interrupt.h>
+#include <linux/nsproxy.h>
+#include <linux/compat.h>
+#include <linux/if_tun.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/cdev.h>
+#include <linux/idr.h>
+#include <linux/fs.h>
+#include <linux/uio.h>
+
+#include <net/net_namespace.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+#include <linux/virtio_net.h>
+
+#define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
+		      NETIF_F_TSO6 | NETIF_F_UFO)
+
+static dev_t ipvtap_major;
+static struct cdev ipvtap_cdev;
+
+static const void *ipvtap_net_namespace(struct device *d)
+{
+	struct net_device *dev = to_net_dev(d->parent);
+	return dev_net(dev);
+}
+
+static struct class ipvtap_class = {
+	 .name = "ipvtap",
+	 .owner = THIS_MODULE,
+	 .ns_type = &net_ns_type_operations,
+	 .namespace = ipvtap_net_namespace,
+};
+
+struct ipvtap_dev {
+	struct ipvl_dev vlan;
+	struct tap_dev	  tap;
+};
+
+static void ipvtap_count_tx_dropped(struct tap_dev *tap)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	this_cpu_inc(vlan->pcpu_stats->tx_drps);
+}
+
+static void ipvtap_count_rx_dropped(struct tap_dev *tap)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	ipvlan_count_rx(vlan, 0, 0, 0);
+}
+
+static void ipvtap_update_features(struct tap_dev *tap,
+				   netdev_features_t features)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	vlan->sfeatures = features;
+	netdev_update_features(vlan->dev);
+}
+
+static int ipvtap_newlink(struct net *src_net,
+			  struct net_device *dev,
+			  struct nlattr *tb[],
+			  struct nlattr *data[])
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+	int err;
+
+	INIT_LIST_HEAD(&vlantap->tap.queue_list);
+
+	/* Since macvlan supports all offloads by default, make
+	 * tap support all offloads also.
+	 */
+	vlantap->tap.tap_features = TUN_OFFLOADS;
+	vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped;
+	vlantap->tap.update_features =	ipvtap_update_features;
+	vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped;
+
+	err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap);
+	if (err)
+		return err;
+
+	/* Don't put anything that may fail after macvlan_common_newlink
+	 * because we can't undo what it does.
+	 */
+	err =  ipvlan_link_new(src_net, dev, tb, data);
+	if (err) {
+		netdev_rx_handler_unregister(dev);
+		return err;
+	}
+
+	vlantap->tap.dev = vlantap->vlan.dev;
+
+	return err;
+}
+
+static void ipvtap_dellink(struct net_device *dev,
+			   struct list_head *head)
+{
+	struct ipvtap_dev *vlan = netdev_priv(dev);
+
+	netdev_rx_handler_unregister(dev);
+	tap_del_queues(&vlan->tap);
+	ipvlan_link_delete(dev, head);
+}
+
+static void ipvtap_setup(struct net_device *dev)
+{
+	ipvlan_link_setup(dev);
+	dev->tx_queue_len = TUN_READQ_SIZE;
+	dev->priv_flags &= ~IFF_NO_QUEUE;
+}
+
+static struct rtnl_link_ops ipvtap_link_ops __read_mostly = {
+	.kind		= "ipvtap",
+	.setup		= ipvtap_setup,
+	.newlink	= ipvtap_newlink,
+	.dellink	= ipvtap_dellink,
+	.priv_size	= sizeof(struct ipvtap_dev),
+};
+
+static int ipvtap_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ipvtap_dev *vlantap;
+	struct device *classdev;
+	dev_t devt;
+	int err;
+	char tap_name[IFNAMSIZ];
+
+	if (dev->rtnl_link_ops != &ipvtap_link_ops)
+		return NOTIFY_DONE;
+
+	snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex);
+	vlantap = netdev_priv(dev);
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		/* Create the device node here after the network device has
+		 * been registered but before register_netdevice has
+		 * finished running.
+		 */
+		err = tap_get_minor(ipvtap_major, &vlantap->tap);
+		if (err)
+			return notifier_from_errno(err);
+
+		devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+		classdev = device_create(&ipvtap_class, &dev->dev, devt,
+					 dev, tap_name);
+		if (IS_ERR(classdev)) {
+			tap_free_minor(ipvtap_major, &vlantap->tap);
+			return notifier_from_errno(PTR_ERR(classdev));
+		}
+		err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj,
+					tap_name);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+	case NETDEV_UNREGISTER:
+		/* vlan->minor == 0 if NETDEV_REGISTER above failed */
+		if (vlantap->tap.minor == 0)
+			break;
+		sysfs_remove_link(&dev->dev.kobj, tap_name);
+		devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+		device_destroy(&ipvtap_class, devt);
+		tap_free_minor(ipvtap_major, &vlantap->tap);
+		break;
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		if (tap_queue_resize(&vlantap->tap))
+			return NOTIFY_BAD;
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ipvtap_notifier_block __read_mostly = {
+	.notifier_call	= ipvtap_device_event,
+};
+
+static int ipvtap_init(void)
+{
+	int err;
+
+	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap");
+
+	if (err)
+		goto out1;
+
+	err = class_register(&ipvtap_class);
+	if (err)
+		goto out2;
+
+	err = register_netdevice_notifier(&ipvtap_notifier_block);
+	if (err)
+		goto out3;
+
+	err = ipvlan_link_register(&ipvtap_link_ops);
+	if (err)
+		goto out4;
+
+	return 0;
+
+out4:
+	unregister_netdevice_notifier(&ipvtap_notifier_block);
+out3:
+	class_unregister(&ipvtap_class);
+out2:
+	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+out1:
+	return err;
+}
+module_init(ipvtap_init);
+
+static void ipvtap_exit(void)
+{
+	rtnl_link_unregister(&ipvtap_link_ops);
+	unregister_netdevice_notifier(&ipvtap_notifier_block);
+	class_unregister(&ipvtap_class);
+	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+}
+module_exit(ipvtap_exit);
+MODULE_ALIAS_RTNL_LINK("ipvtap");
+MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_LICENSE("GPL");